Domain Decomposition with Neural Network Interface Approximations for time-harmonic Maxwell’s equations with different wave numbers

• Autores: Knoke, Tobias, Kinnewig, Sebastian, Beuchler, Sven, Demircan, Ayhan, Morgner, Uwe, Wick, Thomas
• Formato: artículo
• Fecha de Publicación: 2023
• Institución: Universidad Nacional de Trujillo
• Repositorio: Revistas - Universidad Nacional de Trujillo
• Lenguaje: inglés
• OAI Identifier: oai:ojs.revistas.unitru.edu.pe:article/5045
• Enlace del recurso: https://revistas.unitru.edu.pe/index.php/SSMM/article/view/5045
• Nivel de acceso: acceso abierto
• Materia: Time-Harmonic Maxwell’s Equations; Machine Learning; Feedforward Neural Network; Domain Decomposition Method

In this work, we consider the time-harmonic Maxwell’s equations and their numerical solution with a domain decomposition method. As an innovative feature, we propose a feedforward neural network-enhanced approximation of the interface conditions between the subdomains. The advantage is that the interface condition can be updated without recomputing the Maxwell system at each step. The main part consists of a detailed description of the construction of the neural network for domain decomposition and the training process. To substantiate this proof of concept, we investigate a few subdomains in some numerical experiments with low frequencies. Therein the new approach is compared to a classical domain decomposition method. Moreover, we highlight current challenges of training and testing with different wave numbers and we provide information on the behaviour of the neural-network, such as convergence of the loss function, and different activation functions.